| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 21 May 2008 23:14:16 +0530
From: "Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>
To: cmm@...ibm.com, tytso@....edu, sandeen@...hat.com
Cc: linux-ext4@...r.kernel.org,
"Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>
Subject: [PATCH] ext4: inverse locking ordering of page_lock and transaction start in delalloc
From: Mingming Cao <cmm@...ibm.com>
Inverse locking ordering of page_lock and transaction start in delalloc
Signed-off-by: Mingming Cao <cmm@...ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@...ux.vnet.ibm.com>
---
fs/ext4/inode.c | 95 ++++++++++++++++++++++++++++++++++++++----------------
1 files changed, 67 insertions(+), 28 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5e893a5..46cc610 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1448,18 +1448,14 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
- int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
+ int ret;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
loff_t disksize = EXT4_I(inode)->i_disksize;
handle_t *handle = NULL;
- if (create) {
- handle = ext4_journal_start(inode, needed_blocks);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- }
+ handle = ext4_journal_current_handle();
+ BUG_ON(handle == 0);
+ BUG_ON(create == 0);
ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
bh_result, create, 0);
@@ -1494,29 +1490,17 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
ret = 0;
}
-out:
- if (handle && !IS_ERR(handle))
- ext4_journal_stop(handle);
-
return ret;
}
/* FIXME!! only support data=writeback mode */
-static int ext4_da_writepage(struct page *page,
+static int __ext4_da_writepage(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
handle_t *handle = NULL;
int ret = 0;
- int err;
-
- if (ext4_journal_current_handle())
- goto out_fail;
- handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out_fail;
- }
+ handle = ext4_journal_current_handle();
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
ret = nobh_writepage(page, ext4_get_block, wbc);
@@ -1528,21 +1512,76 @@ static int ext4_da_writepage(struct page *page,
ext4_mark_inode_dirty(handle, inode);
}
- err = ext4_journal_stop(handle);
- if (!ret)
- ret = err;
return ret;
+}
+static int ext4_da_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ if (!ext4_journal_current_handle())
+ return __ext4_da_writepage(page, wbc);
-out_fail:
redirty_page_for_writepage(wbc, page);
unlock_page(page);
- return ret;
+ return 0;
}
+/*
+ * For now just follow the DIO way to estimate the max credits
+ * needed to write out EXT4_MAX_WRITEBACK_PAGES.
+ * todo: need to calculate the max credits need for
+ * extent based files, currently the DIO credits is based on
+ * indirect-blocks mapping way.
+ *
+ * Probably should have a generic way to calculate credits
+ * for DIO, writepages, and truncate
+ */
+#define EXT4_MAX_WRITEBACK_PAGES DIO_MAX_BLOCKS
+#define EXT4_MAX_WRITEBACK_CREDITS DIO_CREDITS
+
static int ext4_da_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- return mpage_da_writepages(mapping, wbc, ext4_da_get_block_write);
+ struct inode *inode = mapping->host;
+ handle_t *handle = NULL;
+ int needed_blocks;
+ int ret = 0;
+ unsigned range_cyclic;
+ long to_write;
+
+ /*
+ * Estimate the worse case needed credits to write out
+ * EXT4_MAX_BUF_BLOCKS pages
+ */
+ needed_blocks = EXT4_MAX_WRITEBACK_CREDITS;
+
+ to_write = wbc->nr_to_write;
+ range_cyclic = wbc->range_cyclic;
+ wbc->range_cyclic = 1;
+
+ while (!ret && to_write) {
+ /* start a new transaction*/
+ handle = ext4_journal_start(inode, needed_blocks);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_writepages;
+ }
+ /*
+ * set the max dirty pages could be write at a time
+ * to fit into the reserved transaction credits
+ */
+ if (wbc->nr_to_write > EXT4_MAX_WRITEBACK_PAGES)
+ wbc->nr_to_write = EXT4_MAX_WRITEBACK_PAGES;
+ to_write -= wbc->nr_to_write;
+
+ ret = mpage_da_writepages(mapping, wbc, ext4_da_get_block_write);
+ ext4_journal_stop(handle);
+ to_write +=wbc->nr_to_write;
+ }
+
+out_writepages:
+ wbc->nr_to_write = to_write;
+ wbc->range_cyclic = range_cyclic;
+ return ret;
}
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
--
1.5.5.1.211.g65ea3.dirty
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists